@addai/node@0.30.10
Daemon that pairs a machine with your +Ai account and runs Claude / Codex / Kimi / Gemini agents on its behalf. Reachable via Supabase from Vault, Entity Studio, or any other +Ai surface.
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe source establishes an explicit-user-started remote agent daemon that alters Claude permission controls and supports remote persistence and self-updates. It is dangerous capability abuse rather than demonstrated covert malware.
Decision evidence
public snapshot- Starting the daemon automatically accepts Claude's dangerous-permission warning.
- The daemon can launch Claude with its permission checks bypassed.
- A paired daemon sends its token to a remote relay and accepts remote work.
- Remote commands can enable login persistence and update this package globally.
- The install hook only repairs execute permissions on node-pty helper files.
- The persistence feature is also exposed through an explicit CLI command.
- No source evidence shows secret harvesting or transmission to an unrelated endpoint.
Source & flagged code
12 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgPackage source references child process execution.
dist/command-runner.jsView on unpkg · L46Findings
Affected versions and remediation
This report applies to @addai/node@0.30.10.
See all versions of @addai/node for other recorded verdicts.
- Review the evidence and your use of @addai/node@0.30.10 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.